Microsoft · AI-103
Text analysis and translation
AI-103 · Lesson 12 of 15 · 1:33:24
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the AI-103 exam (Azure AI Apps and Agents Developer Associate). In this lesson: two approaches to text analysis (a model with structured outputs, or Azure Language), Azure Language core and legacy features, Azure Language in Python (language detection, entities, PII detection and redaction policies), structured output rules and Content Safety for text, and translation with Azure Translator (neural or GPT-based, tone and gender, Custom Translator, adaptive custom translation, document translation) and domain tasks. Includes three original practice questions.
Preview the topics
- Chat logs must be stored with phone numbers and email addresses hidden, but the type of each hidden value must stay visible, like [PHONE_1]. What should you use?
- A strict schema for support messages needs an order number field that’s sometimes absent from the text. How should you define it?
- A travel company uses Translator to send French replies to customers, and wants them in a formal register. What should each request specify for the French target?